DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation Qingkai Fang 1,2, Y an Zhou 1,2, Y ang Feng 1,2 1

Feb-17-2026, 16:32:38 GMT–Neural Information Processing Systems 

In this paper, we propose DASpeech, a non-autoregressive direct S2ST model which realizes both fast and high-quality S2ST.